Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
This addresses the challenge of developing robust dialogue systems for enterprises with minimal data, though it is incremental as it builds on existing transfer learning methods.
The paper tackles the problem of few-shot dialogue generation without annotated data by leveraging transfer learning from a larger dataset, achieving state-of-the-art results on the Stanford Multi-Domain Dialogue Dataset with improved BLEU and Entity F1 scores.
Learning with minimal data is one of the key challenges in the development of practical, production-ready goal-oriented dialogue systems. In a real-world enterprise setting where dialogue systems are developed rapidly and are expected to work robustly for an ever-growing variety of domains, products, and scenarios, efficient learning from a limited number of examples becomes indispensable. In this paper, we introduce a technique to achieve state-of-the-art dialogue generation performance in a few-shot setup, without using any annotated data. We do this by leveraging background knowledge from a larger, more highly represented dialogue source --- namely, the MetaLWOz dataset. We evaluate our model on the Stanford Multi-Domain Dialogue Dataset, consisting of human-human goal-oriented dialogues in in-car navigation, appointment scheduling, and weather information domains. We show that our few-shot approach achieves state-of-the art results on that dataset by consistently outperforming the previous best model in terms of BLEU and Entity F1 scores, while being more data-efficient by not requiring any data annotation.